cvprofiles · construct-validity profile
Admissible measurement set under a stated nomological network, and the image of β on that set. Empty sets and wide ranges are scientific features.
[L, U] · method = min/max B*
[0.106829, 0.390598]
Width = 0.283769 · 4 survivors · bootstrap percentile band = [-0.039167, 0.679855]
Target β = ols_coef on outcome log_gdp_pc. Range uses only measures in M*; rejected β values are shown below but never enter [L,U].
| run_id | 7fc7827d89a8587a4b9cfae1e60722832dfb975e65ff62f1ea7d41debeaf8242 |
|---|---|
| package | 3.0.2 |
| scores_hash | 6fdc7534585bac517e1ee86866b3d94b2b62ba1099df7957f2d4ef1516519ac4 |
| network_hash | 1eb3060a9f91564e6f6fecd71212b3d64fb6a717badd396512b25ce4ffddf6e2 |
| beta_hash | 40040c2105c1d9b34e212dddd8ca9487fdb315d4db2ebee0ebaf29129df5cafe |
| δ | 0.0 |
| seed | 20260814 |
| network | trust_country_two_resolution |
Units-only Efron resampling; percentile band over non-empty replicates. The headline [L, U] above remains min/max β(M*) on the full sample.
| replicates | 1000 |
|---|---|
| seed | 20260814 |
| quantiles | [0.025, 0.975] |
| non-empty | 998 |
| empty | 2 (0.002) |
| degenerate | 0 (0.000) |
| band | [-0.039167, 0.679855] |
Per-side α/2 quantiles over non-empty bootstrap replicates (α = 0.1). Heuristic band — not a confidence interval, not a holdout-robustness band. The headline [L, U] above remains min/max β(M*) on the full sample.
| α | 0.1 |
|---|---|
| κ | 2.0 |
| quantiles | [0.05, 0.95] |
| band | [-0.016173, 0.638857] |
| empty rate | 0.002 |
| degenerate rate | 0.000 |
| measure | margin | SE | boundary |
|---|---|---|---|
| m_gps_trust | -0.197064 | 0.156003 | yes |
| m_trust_general | 0.306865 | 0.121299 | no |
| m_trust_in_group | 0.097667 | 0.115791 | yes |
| m_trust_out_group | 0.219973 | 0.113700 | yes |
| m_trust_institution | -0.562602 | 0.125007 | no |
| m_trust_composite | -0.051991 | 0.121575 | yes |
| m_noise | -0.373876 | 0.157089 | no |
| measure | p̂m |
|---|---|
| m_gps_trust | 0.127 |
| m_trust_general | 0.998 |
| m_trust_in_group | 0.910 |
| m_trust_out_group | 0.946 |
| m_trust_institution | 0.001 |
| m_trust_composite | 0.789 |
| m_noise | 0.007 |
Heuristic uncertainty band over non-empty bootstrap replicates (selection uncertainty on the pooled sample; holdout verdict is a full-sample point finding outside the band). Not a confidence interval; not a holdout-robustness band. Boundary attribution: |margin_m| <= kappa * SE_m.
λ scales threshold magnitudes only. λ is never auto-selected; the headline is always λ=1.0. This grid is not part of the freeze preimage.
| λ | |M*| | empty | L | U |
|---|---|---|---|---|
| 0.5 | 4 | no | 0.106829 | 0.390598 |
| 1.0 | 4 | no | 0.106829 | 0.390598 |
| 1.5 | 3 | no | 0.191812 | 0.390598 |
| 2.0 | 2 | no | 0.266456 | 0.390598 |
One pre-data anchor per restriction (hash 68e155f6775d…). The engine enforces completeness + hash; "pre-data" is a process commitment, not a temporal claim.
| restriction | kind | pre-data | anchor |
|---|---|---|---|
| conv_rule_of_law | literature | yes | aghion2010_h5 — Trust–institutions correlations typically ≥0.4 (Aghion, Algan, Cahuc, Shleifer 2010). H5 historical floor 0.30. |
| disc_gini | literature | yes | bjornskov2008_h5 — Bjørnskov 2008: negative trust–inequality relationship. H5 historical θ=0.10 on corr_sign. |
| conv_edu_hold | literature | yes | falk2018_table_v — Falk et al. 2018 Table V: trust increases with cognitive ability in almost all countries. Leftover country-level education bar θ=0.20. |
M* size = 4 / 7. Slack rule: admit if sr(m) ≥ −δ for all r.
| measure | status | β(m) | failed restrictions |
|---|---|---|---|
| m_gps_trust | rejected | 0.109023 | conv_rule_of_law |
| m_trust_general | admissible | 0.390598 | — |
| m_trust_in_group | admissible | 0.191812 | — |
| m_trust_out_group | admissible | 0.266456 | — |
| m_trust_institution | rejected | -0.092285 | conv_rule_of_law |
| m_trust_composite | admissible | 0.106829 | — |
| m_noise | rejected | 0.028351 | conv_rule_of_law, disc_gini |
Positive / zero ≈ satisfied at δ=0.0. Negative = violation magnitude.
| measure | conv_rule_of_law | disc_gini | conv_edu_hold |
|---|---|---|---|
| m_gps_trust | -0.176415 | 0.003543 | -0.197064 |
| m_trust_general | 0.404767 | 0.421874 | 0.306865 |
| m_trust_in_group | 0.182494 | 0.509629 | 0.097667 |
| m_trust_out_group | 0.358501 | 0.219973 | 0.328627 |
| m_trust_institution | -0.424613 | 0.175068 | -0.562602 |
| m_trust_composite | 0.104768 | 0.407739 | -0.051991 |
| m_noise | -0.373876 | -0.004827 | -0.101694 |
Engine does not invent restrictions. Agent may author oracle R for synthetic DGPs only.